Showing papers by "Sebastian Thrun published in 1997"

The dynamic window approach to collision avoidance

Abstract: This approach, designed for mobile robots equipped with synchro-drives, is derived directly from the motion dynamics of the robot. In experiments, the dynamic window approach safely controlled the mobile robot RHINO at speeds of up to 95 cm/sec, in populated and dynamic environments.

Active mobile robot localization

Abstract: Localization is the problem of determining the position of a mobile robot from sensor data. Most existing localization approaches are passive, i.e., they do not exploit the opportunity to control the robot’s effectors during localization. This paper proposes an active localization approach. The approach provides rational criteria for (1) setting the robot’s motion direction (exploration), and (2) determining the pointing direction of the sensors so as to most efficiently localize the robot. Furthermore, it is able to deal with noisy sensors and approximative world models. The appropriateness of our approach is demonstrated empirically using a mobile robot in a structured office environment.

Active mobile robot localization by entropy minimization

Abstract: Localization is the problem of determining the position of a mobile robot from sensor data. Most existing localization approaches are passive, i.e., they do not exploit the opportunity to control the robot's effecters during localization. This paper proposes an active localization approach. The approach provides rational criteria for (1) setting the robot's motion direction (exploration), and (2) determining the pointing direction of the sensors so as to most efficiently localize the robot. Furthermore, it is able to deal with noisy sensors and approximate world models. The appropriateness of our approach is demonstrated empirically using a mobile robot in a structured office environment.

Active mobile robot localization by entropy minimization

Abstract: Localization is the problem of determining the position of a mobile robot from sensor data. Most existing localization approaches are passive, i.e., they do not exploit the opportunity to control the robot's effecters during localization. This paper proposes an active localization approach. The approach provides rational criteria for (1) setting the robot's motion direction (exploration), and (2) determining the pointing direction of the sensors so as to most efficiently localize the robot. Furthermore, it is able to deal with noisy sensors and approximate world models. The appropriateness of our approach is demonstrated empirically using a mobile robot in a structured office environment.

To Know or Not to Know: On the Utility of Models in Mobile Robotics

Abstract: —This article describes Jeeves, one of the winning entries in the 1996 AAAI mobile robot competition. Jeeves tied for first place in the finals of the competition, after it won both preliminary trials. A key aspect in Jeeves’s software design was the ability to acquire a model of the environment. The model, a geometric map constructed from sensory data while the robot performs its task, enabled Jeeves to sweep the arena efficiently. It facilitated the retrieval of balls and their delivery at the gate, and it helped to avoid unintended collisions with obstacles. This paper argues that Jeeves’s success depended crucially on the existence of the model. It also argues that models are generally useful in mobile robotics—even in tasks as simple as the one faced in this competition.

A Probabilistic Approach for Concurrent Map Acquisition and Localization for Mobile Robots

Abstract: : This paper addresses the problem of building large scale geometric maps of indoor environments with mobile robots. It poses the map building problem as a constrained, probabilistic maximum likelihood estimation problem. It then devises a practical algorithm for generating the most likely map from data, along with the most likely path taken by the robot. Experimental results in cyclic environments of size up to 80 by 25 meter illustrate the appropriateness of the approach.

Explanation-based learning for mobile-robot perception

Abstract: Explanation-based neural network learning (EBNN) has recently been proposed as a method for reducing the amount of training data required for reliable generalization, by relying instead on approximate, previously learned knowledge. We present first experiments applying EBNN to the problem of learning object recognition for a mobile robot. In these experiments, a mobile robot traveling down a hallway corridor learns to recognize distant doors based on color camera images and sonar sensations. The previously learned knowledge corresponds to a neural network that recognizes nearby doors, and a second network that predicts the state of the world after travelling forward in the corridor. Experimental results show that EBNN is able to use this approximate prior knowledge to significantly reduce the number of training examples required to learn to recognize distant doors. We also present results of experiments in which networks learned by EBNN (e.g., "there is a door 2 meters ahead") are then used as background knowledge for learning subsequent functions (e.g., "there is a door 3 meters ahead").

The Museum Tourguide Project: Experiences with a Deployed Service Robot

Abstract: The field of robotics is currently undergoing a major change. In the next decade, we will witness the deployment of a rapidly increasing number of service robots, i.e., robots that will directly provide assistance to people in their daily activities. The new application domains pose new challenges for the field of robotics. There is a need for more flexible and robust methods for robot control, along with more natural interactive user interfaces. This talk describes RHINO, a mobile robot that has recently been deployed at the “Deutsches Museum” as an interactive tourguide. RHINO interacts with and provides guided tours to visitors of the museum. Remote users can also monitor and control RHINO’s operation through a Webbased multi-modal interface. This talk will discuss RHINO’s software architecture, which integrates various modules for high-speed navigation, map learning, and user interaction. Empirical results will also be presented, along with lessons that were learned when deploying the robot in the museum. The work has been carried out jointly with W. Burgard, D. Fox, D. Haehnel, D. Schulz, and W. Steiner from the University of Bonn. O-8186-8138-1/97 $10.00

Data Mining at CALD-CMU: Tools, Experiences and Research Directions

Abstract: We describe the data mining problems and solutions that we have encountered in the Center for Automated Learning and Discovery (CALD) at CMU. Speci cally, we describe these settings and their operational characteristics, describe our proposed solutions, list the performance results, and nally outline future research directions.